Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The overhead light hummed in the otherwise silent study, its sterile glow reflecting off the glossy paper. Emily felt a wave of nausea wash over her. Her father’s bucket list. She felt a tremor in her hands as she read it: *Learn to cook a five-course meal*. She gulped, her throat suddenly dry.

The second item was a little more relaxed: *Visit a museum*. Emily felt a shiver run down her spine. The next entry was what caused it: *Go to a casino*. Emily's jaw clenched. The final entry, scrawled with a heavy hand, made her want to retreat: *Publish a book*. She couldn't believe it.

She blinked rapidly, trying to clear her vision. The room seemed to be closing in.

Emotion: terrified

Cluster: Fear / Anxiety
PC1 (Valence): -2.97 Negative
PC2 (Disposition): -0.62

Role in Research

This story is one of 1,000 stories generated for the emotion terrified. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 terrified stories, after denoising with neutral dialogue baselines, produces the terrified emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the terrified vector is projected through the unembedding matrix.

Promoted:
😣0.357
worse0.350
无法0.334
😰0.333
sickening0.322
Suppressed:
la-0.676
a-0.392
de-0.371
"-0.344
happy-0.309